Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slides
    -0.07
    _mask
    -0.07
     diesel
    -0.07
     autoComplete
    -0.07
    zial
    -0.07
     draws
    -0.07
     agendas
    -0.06
    мор
    -0.06
    iba
    -0.06
     such
    -0.06
    POSITIVE LOGITS
    Alternatively
    0.06
     advoc
    0.06
    ipur
    0.06
    hetic
    0.06
     сю
    0.06
    )".
    0.06
    .yml
    0.06
     Differences
    0.06
     "\",
    0.06
    �
    0.06
    Act Density 0.202%

    No Known Activations